Adversarial Attacks on Heterogeneous Multi-Agent Deep Reinforcement Learning System with Time-Delayed Data Transmission
This paper studies the gradient-based adversarial attacks on cluster-based, heterogeneous, multi-agent, deep reinforcement learning (MADRL) systems with time-delayed data transmission. The structure of the MADRL system consists of various clusters of agents. The deep Q-network (DQN) architecture pre...
Main Authors: | Neshat Elhami Fard, Rastko R. Selmic |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-08-01
|
Series: | Journal of Sensor and Actuator Networks |
Subjects: | |
Online Access: | https://www.mdpi.com/2224-2708/11/3/45 |
Similar Items
-
Multi-Agent Deep Q Network to Enhance the Reinforcement Learning for Delayed Reward System
by: Keecheon Kim
Published: (2022-03-01) -
Adversarial attacks on cooperative multi-agent deep reinforcement learning: a dynamic group-based adversarial example transferability method
by: Lixia Zan, et al.
Published: (2023-07-01) -
An anti-collusion attack defense method for physical layer key generation scheme based on transmission delay
by: Xiaowen Wang, et al.
Published: (2023-04-01) -
Securing DNN for smart vehicles: an overview of adversarial attacks, defenses, and frameworks
by: Suzan Almutairi, et al.
Published: (2023-03-01) -
Adversarial Attack and Defense: A Survey
by: Hongshuo Liang, et al.
Published: (2022-04-01)